weiranl commited on
Commit
3d97980
·
verified ·
1 Parent(s): 50af320

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +38 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 576,
12
+ "initializer_range": 0.041666666666666664,
13
+ "intermediate_size": 1536,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 9,
19
+ "num_hidden_layers": 30,
20
+ "num_key_value_heads": 3,
21
+ "pad_token_id": 2,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_interleaved": false,
25
+ "rope_scaling": null,
26
+ "rope_theta": 100000,
27
+ "tie_word_embeddings": true,
28
+ "torch_dtype": "float32",
29
+ "transformers.js_config": {
30
+ "kv_cache_dtype": {
31
+ "fp16": "float16",
32
+ "q4f16": "float16"
33
+ }
34
+ },
35
+ "transformers_version": "4.51.3",
36
+ "use_cache": true,
37
+ "vocab_size": 49152
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9937bda8167d70eda48c162f3392e38e3ec2534aae7ce5fe675ccd6219931292
3
+ size 538095096
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e250ae115c6d21b42cba9cca1c6ce17cbb1bf3e2e56a04322d6749a3e77fc6b0
3
+ size 5304